Incorporating Information Status into Generation Ranking

We investigate the influence of information status (IS) on constituent order in German, and integrate our findings into a loglinear surface realisation ranking model. We show that the distribution of pairs of IS categories is strongly asymmetric. Moreover, each category is correlated with morphosyntactic features, which can be automatically detected. We build a loglinear model that incorporates these asymmetries for ranking German string realisations from input LFG F-structures. We show that it achieves a statistically significantly higher BLEU score than the baseline system without these features.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Aoife Cahill, Arndt Riester
• Keywords: ACL 2009, Computational Linguistics, German String Realisations, Input Lfg F-structures, Realisation Ranking Model